@openwop/openwop-conformance 2.46.9 → 2.46.11

package/CHANGELOG.md

@@ -1,3 +1,14 @@
+## [2.46.11] — 2026-10-15 — a shared id reads the same on every run
+
+- **Ledger reader: one requirement id recorded by two scenario files.** Each file runs in its own worker, and `readLedgerFile` kept whichever line came last, so the row's `assertions` and `scenario` belonged to the worker that finished last. openwop-app's `prompts.resolution-precedes-composition` read 9 then 5 assertions on identical results.
+  - The least certifiable file still decides the result and keeps its detail, so a failure in either file is never masked (unchanged).
+  - New: the files' assertion counts sum, as the in-worker fold already sums legs, and a tie names the first file by name.
+  - **What a host's next bundle shows:** rows witnessed by two files carry the summed count and a fixed scenario. No result changes.
+
+## [2.46.10] — 2026-10-14 — RFC 0244 Accepted (provisional)
+
+- **No assertion changes.** RFC 0244 flips to `Accepted` (provisional) on MyndHyve's certified 2.46.9 cut, so the packed `spec/v1/gaps.json` changes (G9, G10 and G11 close).
+
 ## [2.46.9] — 2026-10-14 — RFC 0244 §D: a fail-closed trial scores 0
 
 - **`v2-eval-trajectory-trials` `0244.fixture-miss-fails`** also asserts `score: 0` on the missed task's summary entry and on each of its `eval.scored` events (RFC 0244 §D, amended in place). Both implementing hosts converged on the rule: without it, `passRule: "mean"` or the aggregate `passScore` could pass a suite whose trials all failed closed.

package/dist/lib/requirement-ledger.js

@@ -136,8 +136,12 @@ export function recordRequirement(requirementId, disposition, detail, extras) {
 export function readLedgerFile(path) {
     if (!existsSync(path))
         return [];
-    const rank = { 'executed-fail': 0, blocked: 1, 'executed-pass': 2, skipped: 3, inapplicable: 4 };
-    const merged = new Map();
+    const rank = CERTIFIABILITY_RANK;
+    // Pass 1, per (id, scenario file). `<=`, not `<`: a per-`it` FOLD (2.37.0)
+    // appends the cumulative row after the leg rows it folded, so on an equal
+    // disposition the LAST line is the one carrying the summed `assertionCount`.
+    // For genuinely duplicate lines the two are identical and the choice is a no-op.
+    const perFile = new Map();
     for (const line of readFileSync(path, 'utf8').split('\n')) {
         if (line.trim() === '')
             continue;
@@ -150,15 +154,32 @@ export function readLedgerFile(path) {
         }
         if (typeof e.requirementId !== 'string' || !DISPOSITIONS.includes(e.disposition))
             continue;
-        const prior = merged.get(e.requirementId);
-        // `<=`, not `<`: a per-`it` FOLD (2.37.0) appends the cumulative row after
-        // the leg rows it folded, so on an equal disposition the LAST line is the
-        // one carrying the summed `assertionCount`. For genuinely duplicate lines
-        // the two are identical and the choice is a no-op.
+        let files = perFile.get(e.requirementId);
+        if (files === undefined)
+            perFile.set(e.requirementId, (files = new Map()));
+        const file = e.scenarioFile ?? '';
+        const prior = files.get(file);
         if (prior === undefined || rank[e.disposition] <= rank[prior.disposition])
-            merged.set(e.requirementId, e);
+            files.set(file, e);
     }
-    return [...merged.values()].sort((a, b) => a.requirementId.localeCompare(b.requirementId));
+    // Pass 2, across files (2.46.11). Two files that witness ONE id run in
+    // different workers, so "last line wins" made the row's `assertionCount` and
+    // `scenarioFile` whichever worker finished last: the same host read 9 then 5
+    // assertions for `prompts.resolution-precedes-composition` with no result
+    // change. The least certifiable file still decides the disposition and keeps
+    // its detail; counts sum, as the in-worker fold sums them; and a tie names
+    // the first file by name, so the row is the same on every run.
+    const merged = [];
+    for (const files of perFile.values()) {
+        const rows = [...files.values()].sort((a, b) => rank[a.disposition] - rank[b.disposition] || (a.scenarioFile ?? '').localeCompare(b.scenarioFile ?? ''));
+        const winner = rows[0];
+        if (rows.length === 1 || !rows.some((r) => r.assertionCount !== undefined)) {
+            merged.push(winner);
+            continue;
+        }
+        merged.push({ ...winner, assertionCount: rows.reduce((n, r) => n + (r.assertionCount ?? 0), 0) });
+    }
+    return merged.sort((a, b) => a.requirementId.localeCompare(b.requirementId));
 }
 /**
  * The disposition for a requirement. **Absent resolves to `blocked`, never to a

package/dist/spec-artifacts.lock.json

@@ -1,5 +1,5 @@
 {
   "package": "@openwop/spec-artifacts",
-  "version": "2.46.9",
-  "stampSha256": "f1b1f96913996ab189402abd465f66f0034775dc7f11b7ec0be033ad924b2482"
+  "version": "2.46.11",
+  "stampSha256": "b0af3678f27c9129382607d287e51888b7940e87a70ecb32ef4056e29fce7d46"
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@openwop/openwop-conformance",
-  "version": "2.46.9",
+  "version": "2.46.11",
   "description": "Black-box conformance suite for OpenWOP hosts (v2 current; v1 scenarios retained for the frozen v1 tree).",
   "repository": {
     "type": "git",
@@ -56,6 +56,6 @@
     "@openwop/spec-artifacts": "file:../spec-artifacts"
   },
   "peerDependencies": {
-    "@openwop/spec-artifacts": "2.46.9"
+    "@openwop/spec-artifacts": "2.46.11"
   }
 }

package/schemas/CORPUS-STAMP.json

@@ -1,17 +1,17 @@
 {
   "_comment": "Provenance of @openwop/spec-artifacts (RFC 0168 §D.2). files: SHA-256 per file; the conformance suite compares the installed peer against dist/spec-artifacts.lock.json at start.",
   "package": "@openwop/spec-artifacts",
-  "version": "2.46.9",
-  "corpusTag": "v2.46.9",
+  "version": "2.46.11",
+  "corpusTag": "v2.46.11",
   "files": {
     "api/.redocly.lint-ignore.yaml": "bf5a8350b88a72fa43f59605ed8d903ed24b6cfccda5e45509c9f6ed9ee4e712",
     "api/asyncapi.yaml": "d5ecb9ee6114582be3b1f662c84bfac9ae96dae7bacb853e461168f70a8e1c7d",
     "api/grpc/openwop.proto": "c3e72bb17cba514ee98feb6434e6c9b6ea6795bfd086489ec69fd882dd1ad977",
     "api/openapi.yaml": "ac6de5303872664b78ff419c035915593e01599e02835e777a0123de1baeb398",
     "api/redocly.yaml": "b0604c89b2ca6d5076ec25725c539dad44a741a811fe524439ee6daef8baa09f",
-    "api/seams-v2.yaml": "24976e53171c747270890e0f2591ccc2630477824c56edc003d00135bb89daea",
-    "api/v2/asyncapi.yaml": "0da749b02294f7e8c9ded99858bb15296b250b0f1a58d28e5a3f9f289e477d34",
-    "api/v2/openapi.yaml": "b05a3b2e80b7348f0f02647dbd117dcda1604010b59da62a9871139f79726311",
+    "api/seams-v2.yaml": "7722f9cf3dcf9e4288bf1ad0087f347fbc1ee53ccd1f27ebde4b01cd9dfe2ba2",
+    "api/v2/asyncapi.yaml": "2faef7d29e10478bfcde17e63f34b436cedc8b8f6aecb44ca8895bd93ad44ebe",
+    "api/v2/openapi.yaml": "78c72788d422b216286a874a2900674cde0222a80cb92b29b9427d15a7d220e7",
     "api/v2/redocly.yaml": "1e66b60e6118ad11a823bb620678be464d99dfe50a40e3e6f93ec9429b88b34c",
     "schemas/README.md": "276fc1d51eb08e14e9127b9fd27761d7046ee33c12000f3a64a801322db8bf58",
     "schemas/a2a-task-state.schema.json": "75d5049dea8bd873ff0e7546f1c60c8d36c219bec7084264360be54a8be30ae1",
@@ -208,14 +208,14 @@
     "schemas/workspace-file.schema.json": "464de85c2a068243084ee9c1d969bc7cd5d8f7948574e58450d6493c38a0e1e4",
     "spec/v1/alias-detectors.json": "22444c22bb88c568339ef512553f9fc38146e22b566d11ab8608f655d688d19c",
     "spec/v1/capability-declaration-classes.json": "e7729aed5c4b4e1dd02abab0530f14cc95f5d4070fe51fb139e7f5cccefa00c6",
-    "spec/v1/core-standard-manifest.json": "baa24251d00109b8fa47b5dfd8c6cecab312b75240ff5519e71f704eb7fd03f0",
+    "spec/v1/core-standard-manifest.json": "2a845db8a673c2f5c95ff752fc7765fb72779abf589595e7bf9989f36216ea39",
     "spec/v1/deprecations.json": "e723bc11d7272c71789ad1303bb7f21809a8a024abf57594f9d5c35dc199ece9",
     "spec/v1/deprecations.schema.json": "3e393c405d2a41b467d8c5e3c468549078df1ce6a6d2588fc488097b95d9b55b",
     "spec/v1/end-of-support.json": "35f0bf3b70fe78b16e2a2fd81a153fc27e703f6c16376c6fe7cdf1f4f2c4e6d4",
     "spec/v1/event-codemap.json": "3da60d884157793a360da532a9fcbbfb5285636db325a74cec94b34622186d97",
     "spec/v1/event-codemap.schema.json": "d05933b2e88103aff51a2f774df97b9bda065e0fc88dbd9b114cc47a32189174",
     "spec/v1/extensions.json": "79a60754aa16cbdbdb604f8e5c00038af535a1690a4d07bd5ff7c38f0256a7bc",
-    "spec/v1/gaps.json": "a3ab3af1f48fe9f36283d296b06970a4dd759d4e3beb731828831f09e8e8f53b",
+    "spec/v1/gaps.json": "3bd864a64f6c9c69a3bfc4178d9c7df8dd625b682c1dbde1656b89a239c5a6f9",
     "spec/v1/gaps.schema.json": "8fd83259f556553c9df0f53e7a82ca8c2a4771d471197f69b4e2ae0ceeacfd66",
     "spec/v1/migrations.json": "4c50760be70cb644d02427bcaf5749606700edf4513f423903cf3b1d12f5c300",
     "spec/v1/migrations.schema.json": "886779aa6c22e646db097f5df210adb018a4dd14a7b815465a18c8a7056c8f72",
@@ -313,9 +313,9 @@
     "spec/v2/path-manifest.json": "7b5679a4dad98c80d855361d88a98c8a4e045af15e310862a05b285b815dc9fc",
     "spec/v2/peer-dependency-aliases.json": "d10299280abee08258502925bc327293ee413e0108cd6e6ec75ff6110653308d",
     "spec/v2/profiles.json": "b382b261c7844798575f7c1b37c934f0da19846016a2337d883d4f5ef6e05479",
-    "spec/v2/release.json": "3d39622c2a2f6e53ad2bc4fc45439006a0877a3b4b4000de5ea4c5fc90863b64",
+    "spec/v2/release.json": "203adbfd38c222e739f8db654cf2bb453d61dcbdb74702949d933fa3dbad9baf",
     "spec/v2/retention-floors.json": "eaf3722d95c79947af1d4269ef85117e126518c588cfcf1a2b21b97269f51624",
-    "spec/v2/surface-baseline.json": "8782769b454e3f781b889d06fe11978bc6da5eb1993935c205bf05c1b09e5d67"
+    "spec/v2/surface-baseline.json": "a566e5a039f75a076bde41640f4ecbea50fbae41bf4581aff69c2dad14b24b6a"
   },
-  "corpusCommit": "30aa92326225c92edeea084e2c3c484ca18e10e8"
+  "corpusCommit": "398b842f0e19e8de6cd6b6c706b51bedcff77356"
 }

package/src/lib/requirement-ledger.ts

@@ -221,8 +221,12 @@ export function recordRequirement(
  */
 export function readLedgerFile(path: string): readonly LedgerEntry[] {
   if (!existsSync(path)) return [];
-  const rank: Record<Disposition, number> = { 'executed-fail': 0, blocked: 1, 'executed-pass': 2, skipped: 3, inapplicable: 4 };
-  const merged = new Map<string, LedgerEntry>();
+  const rank = CERTIFIABILITY_RANK;
+  // Pass 1, per (id, scenario file). `<=`, not `<`: a per-`it` FOLD (2.37.0)
+  // appends the cumulative row after the leg rows it folded, so on an equal
+  // disposition the LAST line is the one carrying the summed `assertionCount`.
+  // For genuinely duplicate lines the two are identical and the choice is a no-op.
+  const perFile = new Map<string, Map<string, LedgerEntry>>();
   for (const line of readFileSync(path, 'utf8').split('\n')) {
     if (line.trim() === '') continue;
     let e: LedgerEntry;
@@ -232,14 +236,32 @@ export function readLedgerFile(path: string): readonly LedgerEntry[] {
       continue;
     }
     if (typeof e.requirementId !== 'string' || !DISPOSITIONS.includes(e.disposition)) continue;
-    const prior = merged.get(e.requirementId);
-    // `<=`, not `<`: a per-`it` FOLD (2.37.0) appends the cumulative row after
-    // the leg rows it folded, so on an equal disposition the LAST line is the
-    // one carrying the summed `assertionCount`. For genuinely duplicate lines
-    // the two are identical and the choice is a no-op.
-    if (prior === undefined || rank[e.disposition] <= rank[prior.disposition]) merged.set(e.requirementId, e);
+    let files = perFile.get(e.requirementId);
+    if (files === undefined) perFile.set(e.requirementId, (files = new Map()));
+    const file = e.scenarioFile ?? '';
+    const prior = files.get(file);
+    if (prior === undefined || rank[e.disposition] <= rank[prior.disposition]) files.set(file, e);
   }
-  return [...merged.values()].sort((a, b) => a.requirementId.localeCompare(b.requirementId));
+  // Pass 2, across files (2.46.11). Two files that witness ONE id run in
+  // different workers, so "last line wins" made the row's `assertionCount` and
+  // `scenarioFile` whichever worker finished last: the same host read 9 then 5
+  // assertions for `prompts.resolution-precedes-composition` with no result
+  // change. The least certifiable file still decides the disposition and keeps
+  // its detail; counts sum, as the in-worker fold sums them; and a tie names
+  // the first file by name, so the row is the same on every run.
+  const merged: LedgerEntry[] = [];
+  for (const files of perFile.values()) {
+    const rows = [...files.values()].sort(
+      (a, b) => rank[a.disposition] - rank[b.disposition] || (a.scenarioFile ?? '').localeCompare(b.scenarioFile ?? ''),
+    );
+    const winner = rows[0]!;
+    if (rows.length === 1 || !rows.some((r) => r.assertionCount !== undefined)) {
+      merged.push(winner);
+      continue;
+    }
+    merged.push({ ...winner, assertionCount: rows.reduce((n, r) => n + (r.assertionCount ?? 0), 0) });
+  }
+  return merged.sort((a, b) => a.requirementId.localeCompare(b.requirementId));
 }
 
 /**